- 26 10月, 2020 3 次提交
-
-
由 卢旭辉 提交于
feat: Integrate CMSIS5 to MACE Micro See merge request applied-machine-learning/sysml/mace!1305
-
由 张志敏 提交于
# Conflicts: # tools/converter.py # tools/python/convert.py # tools/python/transform/base_converter.py # tools/python/utils/config_parser.py
-
由 Zhang Zhimin 提交于
-
- 23 10月, 2020 4 次提交
- 22 10月, 2020 1 次提交
-
-
由 Zhang Zhimin 提交于
-
- 21 10月, 2020 3 次提交
- 20 10月, 2020 1 次提交
-
-
由 Bin Li 提交于
-
- 15 10月, 2020 2 次提交
-
-
由 卢旭辉 提交于
Fix micro matmul bias access bug See merge request applied-machine-learning/sysml/mace!1304
-
由 Zhang Zhimin 提交于
-
- 14 10月, 2020 6 次提交
-
-
由 李超 提交于
fix: fix `Transpose` op's computing error on batch tensor. See merge request applied-machine-learning/sysml/mace!1302
-
由 李超 提交于
perf: opt `reduce` op's performance on GPU See merge request applied-machine-learning/sysml/mace!1301
-
由 luxuhui 提交于
N/A Signed-off-by: NLuxuhui <luxuhui@xiaomi.com> -
由 Riccardo 提交于
Co-authored-by: Ngasgallo <rgall@sertiscorp.com> -
由 卢旭辉 提交于
feat: Add bf16 kernels for MobileNet See merge request applied-machine-learning/sysml/mace!1298
-
由 luxuhui 提交于
N/A Signed-off-by: NLuxuhui <luxuhui@xiaomi.com>
-
- 27 9月, 2020 1 次提交
-
-
由 Bin Li 提交于
-
- 24 9月, 2020 1 次提交
-
-
由 卢旭辉 提交于
perf: Prefer GPU if input ops on different devices See merge request applied-machine-learning/sysml/mace!1297
-
- 23 9月, 2020 1 次提交
-
-
由 Bin Li 提交于
-
- 21 9月, 2020 2 次提交
-
-
由 李超 提交于
feat: support FusedBatchNormV2/FusedBatchNormV3 for tensorflow See merge request applied-machine-learning/sysml/mace!1296
-
由 luxuhui 提交于
N/A Signed-off-by: NLuxuhui <luxuhui@xiaomi.com>
-
- 31 8月, 2020 3 次提交
-
-
由 卢旭辉 提交于
add micro concat op See merge request applied-machine-learning/sysml/mace!1295
-
由 Zhang Zhimin 提交于
-
由 卢旭辉 提交于
Add onnx's Elu operator See merge request applied-machine-learning/sysml/mace!1294
-
- 27 8月, 2020 1 次提交
-
-
由 lichao18 提交于
-
- 25 8月, 2020 1 次提交
-
-
由 卢旭辉 提交于
Add quantized Relu/BiasAdd/Pad/Transpose for CPU See merge request applied-machine-learning/sysml/mace!1292
-
- 21 8月, 2020 1 次提交
-
-
由 李超 提交于
fix: set Deconv2d filter's opencl buffer type to CONV2D_FILTER See merge request applied-machine-learning/sysml/mace!1293
-
- 19 8月, 2020 1 次提交
-
-
由 Bin Li 提交于
-
- 18 8月, 2020 1 次提交
-
-
由 luxuhui 提交于
N/A Signed-off-by: NLuxuhui <luxuhui@xiaomi.com>
-
- 03 8月, 2020 1 次提交
-
-
由 李超 提交于
fix: delete `Delay` op's benchmark code See merge request applied-machine-learning/sysml/mace!1287
-
- 30 7月, 2020 2 次提交
- 22 7月, 2020 1 次提交
-
-
由 Yi-Kai-Chen 提交于
* Margaux dev. * Support Pad, Activation, Mul operator for mnasnet * Support document enhance model * Apply add-init-cache-and-preemption patch * Refine code * Add APU int16 quantization and fix macro bugs * Refine code Co-authored-by: NYungChien Hsu <yungchien.hsu@mediatek.com> Co-authored-by: NEric Chen <eric-yk.chen@mediatek.com>
-
- 20 7月, 2020 3 次提交
-
-
由 卢旭辉 提交于
Update APU support See merge request applied-machine-learning/sysml/mace!1283
-
由 luxuhui 提交于
N/A Signed-off-by: NLuxuhui <luxuhui@xiaomi.com> -
由 李滨 提交于
feat: support extract_image_patches op and support dynamic filter of conv2d/deconv2d See merge request applied-machine-learning/sysml/mace!1286
-